101 citations · 312 across the 33 of their papers we have counts for
4 papers · 1 filter
Koopman Q-learning: Offline Reinforcement Learning via Symmetries of Dynamics
Matthias Weissenbacher, Samarth Sinha, Animesh Garg +1
Offline reinforcement learning leverages large datasets to train policies without interactions with the environment. The learned policies may then be deployed in real-world setting…
Koopman Spectrum Nonlinear Regulators and Efficient Online Learning
Motoya Ohnishi, Isao Ishikawa, Kendall Lowrey +3
Most modern reinforcement learning algorithms optimize a cumulative single-step cost along a trajectory. The optimized motions are often 'unnatural', representing, for example, beh…
Koopman spectral analysis of elementary cellular automata
Keisuke Taga, Yuzuru Kato, Yoshinobu Kawahara +2
We perform a Koopman spectral analysis of elementary cellular automata (ECA). By lifting the system dynamics using a one-hot representation of the system state, we derive a matrix…
Reproducing kernel Hilbert C*-module and kernel mean embeddings
Yuka Hashimoto, Isao Ishikawa, Masahiro Ikeda +3
Kernel methods have been among the most popular techniques in machine learning, where learning tasks are solved using the property of reproducing kernel Hilbert space (RKHS). In th…